ADD file via upload

main.py

@@ -0,0 +1,101 @@
+from operator import itemgetter
+import matplotlib.pyplot as mp
+import jieba
+import string
+import wordcloud
+import csv
+import os
+
+
+def create_file(filepath):
+    """
+    寻找程序所在目录下的所有文本文件,将保存文件名到filename.csv文件中，并打印文本文件名
+    :param filepath: 文本文件存放路径
+    :return: 所找到的文本文件名对应的序号
+    """
+    with open('filename.csv', 'w', encoding='utf-8', newline='') as file_handler:  # 用于清空filename的内容
+        file_writer = csv.writer(file_handler)
+        row = ['file_no', 'filename']
+        file_writer.writerow(row)
+
+    files = os.listdir(filepath)
+    file_no = 0
+    print('files list:')  # 遍历所有文件
+    for filename in files:
+        file_no = file_no + 1
+        print('%d--' % file_no, end='')
+        print(filename)                        #打印文本文件名以及所对应的序号
+        file_handler = open('filename.csv', 'a+', encoding='utf-8', newline='')  # 保存文件名到filename.csv
+        file_writer = csv.writer(file_handler)
+        row = [file_no, filename]
+        file_writer.writerow(row)
+    return file_no
+
+
+def count_word(filename):
+    """
+    统计词汇数
+    :param filename: 想要统计词汇数的文本文件地址
+    :return: 统计的词汇结果
+    """
+    file_txt = open(filename, "r", encoding='utf-8').read()
+    file_txt = file_txt.lower()  # 将文本文件内容的大写字母换成小写字母
+
+    for ch in string.punctuation:  # 将文本中的特殊字符替换为空格
+        file_txt = file_txt.replace(ch, " ")
+
+    words = list(jieba.lcut(file_txt, cut_all=False))  # 分词
+    wordfre = {}
+    for word in words:  # 统计词汇数
+        if word in wordfre:
+            wordfre[word] += 1
+        else:
+            wordfre[word] = 1
+
+    wordfre = sorted(wordfre.items(), key=itemgetter(1), reverse=True)  # 按字典元素的值进行逆序排序
+    for i in range(30):  # 输出前30个词汇
+        print(wordfre[i])
+    return wordfre
+
+
+def create_cloud(numword):
+    """
+    生成词云并将词汇查询结果写入temp文本文件下
+    :param numword: 统计的词汇结果
+    """
+    with open('temp.txt', 'a', encoding='utf-8') as f:  # 将内容写入temp.txt，并不删除文本文件原有内容
+    #  with open('temp.txt', 'a', encoding='utf-8') as f:   #将内容写入temp.txt，并删除文本文件原有内容
+        for i in numword:
+            f.write("%d：%s\n" % (i[1], i[0]))
+    temp_txt = open("temp.txt", "r", encoding='utf-8').read()
+    cloud = wordcloud.WordCloud(font_path='msyhbd.ttc',  # 词云参数设置
+                                width=1000,
+                                height=700,
+                                background_color="white"
+                                )
+    word_cloud = cloud.generate(temp_txt)
+
+    mp.imshow(word_cloud)  # 词云的展示
+    mp.axis('off')
+    mp.show()
+
+
+if __name__ == "__main__":
+    filepath = 'file'  # txt 文本存放路径
+    create_file(filepath)
+    file_no = input("如果要退出，请输入X\n请输入你的选择：")
+    while file_no != 'X':
+        if file_no.isnumeric():  # 判断是否是数字
+            with open('filename.csv', 'r', encoding='utf-8') as fd:
+                TXT = csv.reader(fd)
+                for i in TXT:
+                    if file_no == i[0]:
+                        filename = filepath + '\\' + i[1]
+                        numword = count_word(filename)
+                        create_cloud(numword)
+                        create_file(filepath)
+                else:
+                    file_no = input("请输入正确的：")
+        else:
+            print("输入错误!")
+            file_no = input("请输入正确的:")